Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313134767> ?p ?o ?g. }
- W4313134767 endingPage "677" @default.
- W4313134767 startingPage "660" @default.
- W4313134767 abstract "Estimating 3D poses and shapes in the form of meshes from monocular RGB images is challenging. Obviously, it is more difficult than estimating 3D poses only in the form of skeletons or heatmaps. When interacting persons are involved, the 3D mesh reconstruction becomes more challenging due to the ambiguity introduced by person-to-person occlusions. To tackle the challenges, we propose a coarse-to-fine pipeline that benefits from 1) inverse kinematics from the occlusion-robust 3D skeleton estimation and 2) Transformer-based relation-aware refinement techniques. In our pipeline, we first obtain occlusion-robust 3D skeletons for multiple persons from an RGB image. Then, we apply inverse kinematics to convert the estimated skeletons to deformable 3D mesh parameters. Finally, we apply the Transformer-based mesh refinement that refines the obtained mesh parameters considering intra- and inter-person relations of 3D meshes. Via extensive experiments, we demonstrate the effectiveness of our method, outperforming state-of-the-arts on 3DPW, MuPoTS and AGORA datasets." @default.
- W4313134767 created "2023-01-06" @default.
- W4313134767 creator A5042598615 @default.
- W4313134767 creator A5049737045 @default.
- W4313134767 creator A5053683603 @default.
- W4313134767 creator A5057307965 @default.
- W4313134767 creator A5074442084 @default.
- W4313134767 date "2022-01-01" @default.
- W4313134767 modified "2023-10-18" @default.
- W4313134767 title "Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement" @default.
- W4313134767 cites W1861492603 @default.
- W4313134767 cites W1967554269 @default.
- W4313134767 cites W2032618685 @default.
- W4313134767 cites W2080873731 @default.
- W4313134767 cites W2101032778 @default.
- W4313134767 cites W2135533529 @default.
- W4313134767 cites W2215643317 @default.
- W4313134767 cites W2302255633 @default.
- W4313134767 cites W2483862638 @default.
- W4313134767 cites W2576289912 @default.
- W4313134767 cites W2604375920 @default.
- W4313134767 cites W2605947573 @default.
- W4313134767 cites W2797184202 @default.
- W4313134767 cites W2798637590 @default.
- W4313134767 cites W2888934629 @default.
- W4313134767 cites W2895748257 @default.
- W4313134767 cites W2948467257 @default.
- W4313134767 cites W2962754033 @default.
- W4313134767 cites W2963037989 @default.
- W4313134767 cites W2963150697 @default.
- W4313134767 cites W2963907666 @default.
- W4313134767 cites W2963995996 @default.
- W4313134767 cites W2965523038 @default.
- W4313134767 cites W2975420824 @default.
- W4313134767 cites W2981514602 @default.
- W4313134767 cites W2981637078 @default.
- W4313134767 cites W2981660954 @default.
- W4313134767 cites W2990270790 @default.
- W4313134767 cites W2991530302 @default.
- W4313134767 cites W2998027150 @default.
- W4313134767 cites W2998273692 @default.
- W4313134767 cites W3004162361 @default.
- W4313134767 cites W3009246422 @default.
- W4313134767 cites W3021907900 @default.
- W4313134767 cites W3035191304 @default.
- W4313134767 cites W3035520874 @default.
- W4313134767 cites W3035551320 @default.
- W4313134767 cites W3036133893 @default.
- W4313134767 cites W3103514110 @default.
- W4313134767 cites W3106126861 @default.
- W4313134767 cites W3107880069 @default.
- W4313134767 cites W3109877674 @default.
- W4313134767 cites W3162938128 @default.
- W4313134767 cites W3167491448 @default.
- W4313134767 cites W3167542203 @default.
- W4313134767 cites W3169660519 @default.
- W4313134767 cites W3174042812 @default.
- W4313134767 cites W3174980830 @default.
- W4313134767 cites W3175199633 @default.
- W4313134767 cites W3189677397 @default.
- W4313134767 cites W3204320006 @default.
- W4313134767 cites W3204956438 @default.
- W4313134767 cites W3205538779 @default.
- W4313134767 cites W4205116876 @default.
- W4313134767 cites W4213227564 @default.
- W4313134767 cites W4214586188 @default.
- W4313134767 cites W4214619583 @default.
- W4313134767 cites W4214684804 @default.
- W4313134767 cites W4214770715 @default.
- W4313134767 cites W4285061168 @default.
- W4313134767 cites W4312311094 @default.
- W4313134767 cites W4320061826 @default.
- W4313134767 doi "https://doi.org/10.1007/978-3-031-20065-6_38" @default.
- W4313134767 hasPublicationYear "2022" @default.
- W4313134767 type Work @default.
- W4313134767 citedByCount "1" @default.
- W4313134767 countsByYear W43131347672023 @default.
- W4313134767 crossrefType "book-chapter" @default.
- W4313134767 hasAuthorship W4313134767A5042598615 @default.
- W4313134767 hasAuthorship W4313134767A5049737045 @default.
- W4313134767 hasAuthorship W4313134767A5053683603 @default.
- W4313134767 hasAuthorship W4313134767A5057307965 @default.
- W4313134767 hasAuthorship W4313134767A5074442084 @default.
- W4313134767 hasBestOaLocation W43131347672 @default.
- W4313134767 hasConcept C11413529 @default.
- W4313134767 hasConcept C121332964 @default.
- W4313134767 hasConcept C121684516 @default.
- W4313134767 hasConcept C154945302 @default.
- W4313134767 hasConcept C17816587 @default.
- W4313134767 hasConcept C207467116 @default.
- W4313134767 hasConcept C2524010 @default.
- W4313134767 hasConcept C31487907 @default.
- W4313134767 hasConcept C31972630 @default.
- W4313134767 hasConcept C33923547 @default.
- W4313134767 hasConcept C39920418 @default.
- W4313134767 hasConcept C41008148 @default.
- W4313134767 hasConcept C52102323 @default.
- W4313134767 hasConcept C65909025 @default.